{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:58:15Z","timestamp":1788879495944,"version":"build-2803163510"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272050"],"award-info":[{"award-number":["62272050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302048"],"award-info":[{"award-number":["62302048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Key Lab of AI and Multi-modal Data Processing, United International College","award":["2023-2024"],"award-info":[{"award-number":["2023-2024"]}]},{"DOI":"10.13039\/501100010226","name":"Guangdong Provincial Department of Education","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Institute of Artificial Intelligence and Future Networks and Engineering Center of AI and Future Education, Guangdong Provincial Department of Science and Technology, China"},{"name":"Zhuhai Science-Tech Innovation Bureau","award":["2320004002772"],"award-info":[{"award-number":["2320004002772"]}]},{"name":"Interdisciplinary Intelligence SuperComputer Center of Beijing Normal University, Zhuhai"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tsc.2026.3665250","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:21Z","timestamp":1771276041000},"page":"934-947","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Request Scheduling and Load Balancing for Edge Deployed Large Language Models"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9822-559X","authenticated-orcid":false,"given":"Fangyi","family":"Mou","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University and Beijing Normal- Hong Kong Baptist University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9375-4818","authenticated-orcid":false,"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6268-2559","authenticated-orcid":false,"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300550"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3393230"},{"key":"ref4","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref5","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.1"},{"key":"ref8","first-page":"173","article-title":"Llumnix: Dynamic scheduling for large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Des. Implementation","author":"Sun"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2022.100651"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2023.06.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3139995"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-industry.40"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00040"},{"key":"ref14","first-page":"12312","article-title":"Distributed inference and fine-tuning of large language models over the Internet","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Borzunov"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.04.007"},{"issue":"4","key":"ref18","first-page":"929","article-title":"A task scheduling algorithm for hadoop platform","volume":"8","author":"Chen","year":"2013","journal-title":"J. Comput."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3233532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599453"},{"key":"ref23","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref24","volume-title":"Monitoring With Prometheus","author":"Turnbull","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED60706.2024.10528703"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421285"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620727"},{"key":"ref28","first-page":"199","article-title":"Serving heterogeneous machine learning models on multi-GPU servers with spatio-temporal sharing","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Choi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.34"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3075254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.176"},{"key":"ref33","first-page":"1","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Frantar"},{"key":"ref34","first-page":"1","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. 3rd Int. Workshop Paraphrasing","author":"Dolan"},{"key":"ref35","first-page":"4149","article-title":"Commonsenseqa: A question answering challenge targeting commonsense knowledge","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Talmor"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1454"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.814"},{"key":"ref39","article-title":"RULER: What\u2019s the real context size of your long-context language models?","author":"Hsieh","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.776"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"ref42","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref43","article-title":"Kubernetes documentation","year":"2026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6456242"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.32"},{"key":"ref46","article-title":"PyTorch documentation"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4629386\/11479482\/11397342-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11479482\/11397342.pdf?arnumber=11397342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:36:55Z","timestamp":1776109015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2026.3665250","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}